Abstract
Ethernet networks are becoming increasingly popular in industrial computercontrolled systems, as they allow for a single network protocol at both the higher and the lower levels of an industrial communication infrastructure. Despite the introduction in the early 90s of a full-duplex operating mode, numerous industrial Ethernet networks still operate in heterogeneous environments, with Ethernet Switching Hubs interconnecting both independent node stations and industrial Ethernet Repeater Hubs. Among node stations interconnected by a Repeater Hub, the network still operates in the traditional shared Ethernet mode; that is, collisions are solved by means of a probabilistic contention resolution algorithm i.e., the medium access is inherently non-deterministic. In this paper, it is analyzed an enhanced collision resolution algorithm for shared Ethernet networks, referred as high priority Binary Exponential Backoff (h-BEB). Such algorithm allows the coexistence of Ethernet standard devices together with modified (real-time) devices in the same network segment. Both the analytical and the simulation timing analysis show that the h-BEB algorithm guarantees a maximum access delay that is significantly smaller than for the case of standard Ethernet stations. Such enhanced collision resolution algorithm enables the traffic separation between standard and modified (real-time) stations, and is therefore able to guarantee a real-time communication behavior in unconstrained traffic environments.

Abstract
This paper presents an architecture (Multi-µ) being implemented to study and develop software based fault tolerant mechanisms for Real-Time Systems, using the Ada language (Ada 95) and Commercial Off-The-Shelf (COTS) components. Several issues regarding fault tolerance are presented and mechanisms to achieve fault tolerance by software active replication in Ada 95 are discussed. The Multi-µ architecture, based on a specifically proposed Fault Tolerance Manager (FTManager), is then described. Finally, some considerations are made about the work being done and essential future developments. © 1998 ACM.

Abstract

Abstract
This paper provides a comprehensive study on how to support time critical distributed applications using PROFIBUS. We show that, despite the absence of synchronous bandwidth allocation, it is possible to guarantee real-time behaviour for the high-priority traffic in PROFIBUS networks. The main contribution of this paper is to give a methodology for the setting of the T-TR parameter, by proper analysis of the worst-case real token rotation time (T-RR).

Abstract

Abstract